Ivan Tikhonov
Deep Learning Engineer at Intel Corporation
Nizhny Novgorod Metropolitan Area Russia
Summary
🤩
Rockstar🎓
Top SchoolIvan Tikhonov is a Deep Learning Engineer with nine years of experience building production-grade C++ and Python systems for AI inference and graphics tooling at Intel, currently contributing to the OpenVINO toolkit. He designs and implements graph transformations, layer support (RNN/GRU/LSTM) and optimization passes, and has a strong track record fixing tricky shape-inference, memory and constant-folding bugs in high-profile open-source projects like OpenVINO and nGraph. Comfortable across low-level C++11/14, boost, modern DL frameworks and frontends (TensorFlow/ONNX), he pairs rigorous academic training (honors MS/BS in Computer Science) with hands-on deployment experience. Notably, his work spans both backend inference optimizations and tooling-level performance analysis, reflecting a rare blend of compiler-style transformations and systems-level engineering.
9 years of coding experience
3 years of employment as a software developer
Master's degree, Computer science and engineering, GPA: 5.0/5.0, graduated with honors, Master's degree, Computer science and engineering, GPA: 5.0/5.0, graduated with honors at Нижегородский Государственный Технический Университет им. Р.Е.Алексеева (НГТУ)
English, Russian
Github Skills (19)
c-language10
operation10
tensorrt10
graph10
openvino10
tensorflow10
tensor10
cprogramming-language10
inference9
shapes9
ai9
deep-learning9
computer-vision9
constant-folding8
cmake8
Programming languages (3)
Github contributions (5)
openvinotoolkit/openvino
May 2020 - Jan 2023
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer
Back-end DeveloperContributions:2514 reviews, 116 commits, 449 PRs in 2 years 8 months
Contributions summary:Ivan appears to be focused on the development of the OpenVINO toolkit's core functionality, specifically concerning optimization and deployment of AI inference. The user's commits demonstrate their work on constant folding for the Concat operation and handling of the DeepToSpace layer transformation. Furthermore, they are involved in the implementation of various other operations and features within the OpenVINO toolkit. The user is also involved in modifications related to TensorFlow frontend support and fixing memory related issues.
inference-enginepytorchmodel-optimizerdeep-learninggpu
NervanaSystems/ngraph
Sep 2019 - May 2020
nGraph - open source C++ library, compiler and runtime for Deep Learning
Role in this project:Back-end Developer
Back-end DeveloperContributions:39 commits, 15 PRs, 82 pushes in 7 months
Contributions summary:Ivan's primary contribution focused on implementing and debugging dynamic slice functionality, specifically for the nGraph library. They addressed bugs related to the TensorIterator, fixed shape inference issues for the body, and incorporated new tests to cover dynamic dimension and different use cases. They also addressed issues related to constant folding for strided slice operations. Additionally, the user made enhancements to the TensorIterator's reshape support.
inference-enginecppc-librarydeep-learningtvm
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.